CN113100709A - Anesthesia depth monitoring system and anesthesia depth monitoring method - Google Patents
Anesthesia depth monitoring system and anesthesia depth monitoring method Download PDFInfo
- Publication number
- CN113100709A CN113100709A CN202110327529.4A CN202110327529A CN113100709A CN 113100709 A CN113100709 A CN 113100709A CN 202110327529 A CN202110327529 A CN 202110327529A CN 113100709 A CN113100709 A CN 113100709A
- Authority
- CN
- China
- Prior art keywords
- signal
- data
- module
- screening
- controller
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4821—Determining level or depth of anaesthesia
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
- A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/40—Detecting, measuring or recording for evaluating the nervous system
- A61B5/4005—Detecting, measuring or recording for evaluating the nervous system for evaluating the sensory system
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/726—Details of waveform analysis characterised by using transforms using Wavelet transforms
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/74—Details of notification to user or communication with user or patient ; user input means
- A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms
Abstract
The invention belongs to the field of anesthesia monitoring, and discloses an anesthesia depth monitoring system and an anesthesia depth monitoring method, wherein the anesthesia depth monitoring system comprises: the monitoring module comprises an electroencephalogram signal monitor, an electrocardiosignal monitor, a pulse signal monitor, a respiration signal monitor, a muscle signal monitor and a perception stimulator and is used for acquiring real-time state signals of patients, and the signal processing module comprises a signal collector and an amplifying circuit. The anesthesia monitoring device can continuously monitor and display the change of the anesthesia depth in real time, better reflect the change of the concentration of the anesthetic and the change of the stimulation of the operation, reduce the risks of the operation and the anesthesia, truly reflect the signal state after the acquired signals are filtered and denoised, is not easily interfered by other signals, and is suitable for popularization and application in medical institutions.
Description
Technical Field
The invention belongs to the field of anesthesia monitoring, and particularly relates to an anesthesia depth monitoring system and an anesthesia depth monitoring method.
Background
Anesthesia is the loss of consciousness of the patient; eliminating pain; resulting in immobility (muscle relaxation); and elimination of unwanted reflexes such as pharyngeal spasms and arrhythmias (reflex suppression). The depth of anesthesia determines whether the patient experiences pain and the time of awareness, and according to clinical statistics, only about two-thirds of patients receive quality anesthesia service, with about 14% of patients being over-anesthetized, 16% of patients being over-anesthetized, and 10% of patients being under shallow time. When the anesthesia is too deep, the drug overdose can cause the respiration to slow down and even stop, and the brain can also lack oxygen, so that the heart of the patient is stopped and the like. If the anesthesia is too shallow, the patient is aware of the operation, and the patient has memory or even feels pain. Monitoring of the depth of anesthesia in a patient is highly desirable.
At present, the technology for monitoring the anesthesia degree of a patient is mainly used for electroencephalogram monitoring of electroencephalograms of cortical layers, no method is available for monitoring the change of the electroencephalograms under the cortex, the signals are often interfered by medical surgical instruments, the monitoring is invalid, the patient is painful, in an anesthesia operation, an anesthesiologist can hardly observe all information of a patient at the same time, the anesthesia process of the patient is shallow or deep, in the operation process, the real-time data of the patient can not be continuously monitored, the stimulation of the anesthesia to the patient and the stimulation state in the operation process can not be reflected, and the technology is not suitable for wide application.
Through the analysis, the problems and the defects of the existing anesthesia depth monitoring system and the anesthesia depth monitoring method are summarized as follows:
1. the existing device and method have poor stability and cannot reflect the change of the concentration of the anesthetic and the change of the surgical stimulation well.
2. The existing device can not monitor the depth signal and can not monitor information of each part of a patient.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides an anesthesia depth monitoring system and an anesthesia depth monitoring method.
In order to realize the aim, the anesthesia depth monitoring system comprises a monitor module, a signal processing module, a central control module, a display module and a monitoring alarm module;
the monitor module is connected with the central control module, consists of an electroencephalogram signal monitor, an electrocardiosignal monitor, a pulse signal monitor, a respiration signal monitor, a muscle signal monitor and a perception stimulator and is used for acquiring real-time body state signals of patients;
the signal processing module is connected with the central control module and comprises a signal collector and an amplifying circuit, wherein the signal collector is used for collecting the body state signal collected by the monitor, the signal is amplified through the amplifying circuit, the signal is denoised by using wavelet packet denoising after amplification, the wavelet packet denoising can process noise generated in the transmission process of the signal, and the integrity of the signal is ensured;
after the signal collector collects the body state signal, the signal collector carries out primary processing on the body state signal, and the processing method comprises the following steps:
generating an estimated signal value for a particular signal component in the input signal;
the calculation formula of the estimated signal value is as follows:
wherein i is a positive integer and is equal to or less than the number of types of the input signal, K is a positive integer and is equal to or less than the number K of the nodes,for the estimated signal value, S, corresponding to the i-th input signali(n) is the i-th input signal, xk(n) is the input signal of the kth node;
generating a signal processing result according to the input signal and the estimated signal value;
adjusting the estimated signal value according to the signal processing result to output a target estimated signal of a specific signal component in the input signal;
the central control module is connected with the monitor module, the signal processing module, the display module, the data monitoring module and the monitoring alarm module, comprises a controller, an A/D converter and a D/A converter, and is used for processing feedback signals of all machines and realizing transmission of control signals;
the processing of the feedback signals of the various machines comprises: determining a linear relationship between a physical quantity of an AD conversion object and a corresponding voltage value; judging whether the voltage value measured under the current physical quantity has deviation, and if the deviation exists, automatically performing AD conversion calibration by the controller;
the controller automatically performs AD conversion calibration, including:
connecting and setting parameters of the controller and testing the operating characteristics of the controller; the operational characteristics of the test controller include: the controller is enabled to be in a speed mode, so that the controller is enabled to control and correct, and the stable performance of the speed inner ring is ensured; the designed MFAC control algorithm is built on an upper PC through Simulink of cSPACE; running a compilation module in the MFAC controller; automatically generating DSP codes by using an MFAC algorithm; downloading the codes into a digital signal processor through a USB interface of an upper PC for operation, generating a voltage output signal through a controller, and driving the controller to operate;
the MFAC control method is realized by programming:
the MFAC controller u (k) is built partially based on Simulink of cSPACE, and lambda > 0 is a weight coefficient and is used for limiting the change of a control input quantity; rho epsilon (0, 1)]The step size factor is additionally added, so that the algorithm has stronger flexibility and generality;is an estimate of phi (k) at time k; y (k +1) is the desired output signal; u (k), y (k) respectively represent the input and output of the system at time k;
the MFAC controller u (k) is built in part from Simulink of cSPACE, and comprises:
u (k) is subjected to a time delay module to obtain u (k-1); a sinusoidal position signal, namely y (k +1), is given by a sine wave module in the cSPACE; the output y (k +1) of the linear motor can be obtained by the grating detection unit, and then y (k) is obtained by the delay module; the lambda and rho values in the MFAC control law algorithm can be directly adjusted online by WM-Write2 and WM-Write3 in cSPACE; the output of the estimator is connected to the In end of the Subsystem, and the output Out is obtainedy (k) is connected to the desired signal y (k +1) in a negative feedback manner, thereby obtaining y (k +1) -y (k); the output is inserted into the Product module to obtainAccessing the output sum u (k-1) into the Add block, wherein Listofsigns in the Add block is set to (+ + -E); obtaining an output signal u (k) of the MFAC controller;
wherein, mu is more than 0, eta belongs to (0, 1)];The pseudo-partial derivative of the previous time instant of representation;
Δy(k)=y(k)-y(k-1);Δu(k-1)=u(k-1)-u(k-2);
substituting the pseudo partial derivatives into the formulaThereby obtaining a controller output u (k);
the controller outputs u (k), and then the digital signal is converted into an analog signal through the D/A converter; the analog signal is regenerated into a voltage output signal to drive operation;
the display module is connected with the central control module and is formed by connecting three display screens, the left display screen is used for displaying pulse signals and muscle signals, the middle display screen is used for displaying brain signals, electrocardio signals and respiratory signals, and the right display screen is used for displaying perception stimulation signals and anesthesia depth data;
the data monitoring module is connected with the central control module and is used for analyzing the data transmitted by the central control module in real time and screening whether abnormal data exist or not;
and the alarm module is connected with the central control module and used for sending alarm prompt by using the alarm when abnormal data is detected.
Further, the data monitoring module comprises a data reading unit, a data screening unit, an abnormal database unit and a parameter setting unit, and the screening method of the data monitoring module on the abnormal data comprises the following steps:
setting a data range value for screening the acquired data through a parameter setting unit;
the data reading unit is connected with the central control module and reads various processed body state signals;
screening data which accord with the data range value set by the parameter setting unit through the data screening unit, and outputting corresponding statistical abnormal data;
and the abnormal database is connected with the data screening unit and is used for storing the data screened by the data screening unit.
Further, the screening, by the data screening unit, of the data that conforms to the data range value set by the parameter setting unit includes:
screening in a first round, namely screening out data which belong to systematic errors in the data of various body state signals to obtain body state signal data after the first round of screening;
screening for the second round, namely screening out data which do not accord with actual body conditions in the body state signal data after the first round of screening to obtain body state signal data after the second round of screening;
and a third round of screening, namely screening abnormal and continuous data in the body state signal data after the second round of screening to obtain body state signal data after the third round of screening.
Further, the method for amplifying the signal by the amplifying circuit comprises the following steps:
receiving body state signals collected by a signal collector, and respectively sending the body state signals to a coil branch and a reference branch;
in the coil branch, the transmitting coil transmits an electromagnetic signal, the receiving coil receives an induced signal, and an output signal of the receiving coil is amplified;
and then sent to a central control module for processing, wherein the central control module generates an adjustable amplification control signal to further control the adjustable amplifier.
And further, a phase shifter is arranged in one of the coil branch or the reference branch, and the phase shifter shifts the phase of the branch signal according to the phase shift control signal.
Further, the alarm module comprises an audible and visual alarm and a wireless signal transmitter, the audible and visual alarm is used for sending audible and visual alarm signals, and the wireless signal transmitter is used for transmitting the alarm signals to a remote monitoring terminal.
Furthermore, the electrocardiosignal monitor, the muscle signal monitor and the brain signal monitor realize real-time signal acquisition of patients through the electrode patches.
Further, the anesthesia depth monitoring system further comprises:
the data storage module is connected with the central control module and is used for realizing the real-time storage of the patient information through the memory;
and the evaluation module is connected with the central control module and used for sending a request for requesting data to the central control module through an evaluation program, the request information reaches the switch, the switch is sent to the router, the router is sent to the server of the DNS server reaching the main controller, the server receives the request for requesting data, the data to be counted are packaged and packaged, the original path is returned to the evaluation module, the data are decoded, and the current anesthesia depth of the patient is analyzed through the evaluation program.
Further, the evaluation program uses the trained deep convolutional neural network to perform calculation evaluation on the data, and specifically includes:
annotating the body state signal data to establish a training data set comprising a first assessment score;
training the deep convolutional neural network through a training data set to reduce a difference between a second evaluation score output by the deep convolutional neural network corresponding to the input body state signal and a first evaluation score of the input body state signal through training.
Further, the first evaluation score is obtained by performing preliminary quality evaluation on the body state signal according to a preset anesthesia depth parameter.
By combining all the technical schemes, the invention has the advantages and positive effects that:
the device and the method can continuously monitor and display the change of the anesthesia depth in real time, create good operation conditions, better reflect the change of the concentration of the anesthetic and the change of operation stimulation, reduce the operation and anesthesia risks, have a mature signal acquisition method, truly reflect the signal state by filtering and denoising the acquired signals, are not easily interfered by other signals, and are suitable for popularization and application in medical institutions. And the signal processing module is used for processing the signal, so that the detection capability of the invention on the body state signal is greatly improved, and the situations of missing report and false report are greatly reduced.
Drawings
FIG. 1 is a schematic structural diagram of a display screen in an anesthesia depth monitoring system according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of an anesthesia depth monitoring system provided by an embodiment of the present invention;
in the figure, 1, left screen; 2. a middle screen; 3. a right screen; 4. a display module; 5. a monitor module; 6. a signal processing module; 7. a central control module; 8. a data storage module; 9. a data monitoring module; 10. an alarm module; 11. and an evaluation module.
Fig. 3 is a flowchart of a method for monitoring anesthesia depth according to an embodiment of the present invention.
Fig. 4 is a flowchart of a method for performing preliminary processing on a body state signal after the body state signal is acquired by the signal acquisition unit according to the embodiment of the present invention.
Fig. 5 is a flowchart of a method for screening abnormal data by a data monitoring module according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail with reference to the following embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The device and the method can continuously monitor and display the change of the anesthesia depth in real time, create good operation conditions, better reflect the change of the concentration of the anesthetic and the change of operation stimulation, reduce the operation and anesthesia risks, have a mature signal acquisition method, truly reflect the signal state by filtering and denoising the acquired signals, are not easily interfered by other signals, and are suitable for popularization and application in medical institutions.
As shown in fig. 1 and fig. 2, the monitoring device comprises a display module 4, a monitor module 5, a signal processing module 6, a central control module 7, a data storage module 8, a monitoring alarm module 9 and an evaluation module 10;
the display module 4 is connected with the central control module and is formed by connecting three display screens, wherein the left display screen is used for displaying pulse signals and muscle signals, the middle display screen is used for displaying brain signals, electrocardio signals and respiratory signals, and the right display screen is used for displaying perception stimulation signals and anesthesia depth data;
the monitor module 5 is connected with the central control module, consists of an electroencephalogram signal monitor, an electrocardiosignal monitor, a pulse signal monitor, a respiration signal monitor, a muscle signal monitor and a perception stimulator, and is used for acquiring real-time body state signals of patients;
the signal processing module 6 is connected with the central control module and comprises a signal collector and an amplifying circuit, wherein the signal collector is used for collecting the body state signal collected by the monitor, the signal is amplified through the amplifying circuit, the signal is denoised by using wavelet packet denoising after amplification, the wavelet packet denoising can process noise generated in the transmission process of the signal, and the integrity of the signal is ensured;
the central control module 7 comprises a controller, an A/D converter and a D/A converter and is used for processing feedback signals of all machines and realizing transmission of control signals;
the data storage module 8 is connected with the central control module and is used for realizing the real-time storage of the patient information through the memory;
the data monitoring module 9 is connected with the central control module and is used for analyzing the data transmitted by the central control module in real time and screening whether abnormal data exists or not;
and the alarm module 10 is connected with the central control module and used for sending alarm reminding by using an alarm when abnormal data is detected.
The evaluation module 11 is composed of a server and an evaluation program, the evaluation program sends a request for data to the central control module 7, the request information reaches a switch, the switch sends to a router, the router sends to a DNS server and reaches the server of the central control module 7, the server receives the request for data, the data to be counted is packaged and packaged, the original path returns to the evaluation module, the data is decoded, and the evaluation program uses a trained deep convolutional neural network to calculate and evaluate the data. For analyzing the patient's current depth of anesthesia through an evaluation program.
As shown in fig. 3, the anesthesia depth monitoring method provided by the embodiment of the present invention includes the following steps:
s101: connecting each monitor with the central control module by using a transmission line;
s102: switching on a power supply circuit;
s103: connecting an electric patch to a patient for anesthesia;
s104: displaying the related data on a display screen;
s105: according to the current state of the patient, the medical staff judges the anesthesia depth most suitable for the patient and performs anesthesia;
s106: the medical staff manually measures the current information of the patient, compares the current information with the measurement result of the instrument, and verifies the accuracy;
s107: and evaluating the data by using an evaluation program to obtain the anesthesia depth.
The invention overcomes the problem that the existing device and method can not reflect the change of the concentration of the anesthetic and the change of the operation stimulation well. Meanwhile, the depth signal monitoring and the monitoring of information of each part of a patient are realized, and the method can be widely applied.
As shown in fig. 4, the method for performing preliminary processing on the body state signal after the signal collector collects the body state signal in the embodiment of the present invention includes:
s201, aiming at a specific signal component in an input signal, generating an estimated signal value;
s202, generating a signal processing result according to the input signal and the estimated signal value;
s203, adjusting the estimated signal value according to the signal processing result to output a target estimated signal of a specific signal component in the input signal;
the calculation formula of the estimated signal value in the embodiment of the invention is as follows:
wherein i is a positive integer and is equal to or less than the number of types of the input signal, K is a positive integer and is equal to or less than the number K of the nodes,for the estimated signal value, S, corresponding to the i-th input signali(n) is the i-th input signal, xk(n) is the input signal of the kth node;
the data monitoring module in the embodiment of the invention comprises a data reading unit, a data screening unit, an abnormal database unit and a parameter setting unit;
as shown in fig. 5, the method for screening abnormal data by the data monitoring module in the embodiment of the present invention includes:
s301, setting a data range value for screening the acquired data through a parameter setting unit;
s302, connecting the data reading unit with the central control module and reading various processed body state signals;
s303, screening the data which accord with the data range value set by the parameter setting unit through the data screening unit, and outputting corresponding statistical abnormal data;
and S304, the abnormal database is connected with the data screening unit and is used for storing the data screened by the data screening unit.
The method for screening the data which accord with the data range value set by the parameter setting unit through the data screening unit in the embodiment of the invention comprises the following steps:
screening in a first round, namely screening out data which belong to systematic errors in the data of various body state signals to obtain body state signal data after the first round of screening;
screening for the second round, namely screening out data which do not accord with actual body conditions in the body state signal data after the first round of screening to obtain body state signal data after the second round of screening;
and a third round of screening, namely screening abnormal and continuous data in the body state signal data after the second round of screening to obtain body state signal data after the third round of screening.
The method for amplifying the signal by the amplifying circuit in the embodiment of the invention comprises the following steps:
receiving body state signals collected by a signal collector, and respectively sending the body state signals to a coil branch and a reference branch;
in the coil branch, the transmitting coil transmits an electromagnetic signal, the receiving coil receives an induced signal, and an output signal of the receiving coil is amplified;
and then sent to a central control module for processing, wherein the central control module generates an adjustable amplification control signal to further control the adjustable amplifier.
And further, a phase shifter is arranged in one of the coil branch or the reference branch, and the phase shifter shifts the phase of the branch signal according to the phase shift control signal.
In the embodiment of the present invention, processing the feedback signals of the respective machines includes: determining a linear relationship between a physical quantity of an AD conversion object and a corresponding voltage value; judging whether the voltage value measured under the current physical quantity has deviation, and if the deviation exists, automatically performing AD conversion calibration by the controller;
the controller automatically performs AD conversion calibration, including:
connecting and setting parameters of the controller and testing the operating characteristics of the controller; the operational characteristics of the test controller include: the controller is enabled to be in a speed mode, so that the controller is enabled to control and correct, and the stable performance of the speed inner ring is ensured; the designed MFAC control algorithm is built on an upper PC through Simulink of cSPACE; running a compilation module in the MFAC controller; automatically generating DSP codes by using an MFAC algorithm; downloading the codes into a digital signal processor through a USB interface of an upper PC for operation, generating a voltage output signal through a controller, and driving the controller to operate;
the MFAC control method is realized by programming:
the MFAC controller u (k) is built partially based on Simulink of cSPACE, and lambda > 0 is a weight coefficient and is used for limiting the change of a control input quantity; rho epsilon (0, 1)]The step size factor is additionally added, so that the algorithm has stronger flexibility and generality;is an estimate of phi (k) at time k; y (k +1) is the desired output signal; u (k), y (k) respectively represent the input and output of the system at time k;
the MFAC controller u (k) is built in part from Simulink of cSPACE, and comprises:
u (k) is subjected to a time delay module to obtain u (k-1); a sinusoidal position signal, namely y (k +1), is given by a sine wave module in the cSPACE; the output y (k +1) of the linear motor can be obtained by the grating detection unit, and then y (k) is obtained by the delay module; the lambda and rho values in the MFAC control law algorithm can be directly adjusted online by WM-Write2 and WM-Write3 in cSPACE; the output of the estimator is connected to the In end of the Subsystem, and the output Out is obtainedy (k) is connected to the desired signal y (k +1) in a negative feedback manner, thereby obtaining y (k +1) -y (k); the output is inserted into the Product module to obtainAccessing the output sum u (k-1) into the Add block, wherein Listofsigns in the Add block is set to (+ + -E); obtaining an output signal u (k) of the MFAC controller;
wherein, mu is more than 0, eta belongs to (0, 1)];The pseudo-partial derivative of the previous time instant of representation;
Δy(k)=y(k)-y(k-1);Δu(k-1)=u(k-1)-u(k-2);
substituting the pseudo partial derivatives into the formulaThereby obtaining a controller output u (k);
the controller outputs u (k), and then the digital signal is converted into an analog signal through the D/A converter; the analog signal is regenerated into a voltage output signal to drive operation.
The alarm module in the embodiment of the invention comprises an audible and visual alarm and a wireless signal transmitter, wherein the audible and visual alarm is used for sending audible and visual alarm signals, and the wireless signal transmitter is used for transmitting the alarm signals to a remote monitoring terminal.
The electrocardiosignal monitor, the muscle signal monitor and the brain signal monitor in the embodiment of the invention realize the real-time signal acquisition of patients through the electrode patches.
The evaluation program in the embodiment of the invention uses the trained deep convolutional neural network to calculate and evaluate the data, and specifically comprises the following steps:
annotating the body state signal data to establish a training data set comprising a first assessment score;
training the deep convolutional neural network through a training data set to reduce a difference between a second evaluation score output by the deep convolutional neural network corresponding to the input body state signal and a first evaluation score of the input body state signal through training.
Further, the first evaluation score is obtained by performing preliminary quality evaluation on the body state signal according to a preset anesthesia depth parameter.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention, and the scope of the present invention is not limited thereto, and any modification, equivalent replacement, and improvement made by those skilled in the art within the technical scope of the present invention disclosed herein, which is within the spirit and principle of the present invention, should be covered by the present invention.
Claims (10)
1. The anesthesia depth monitoring system is characterized by comprising a monitor module, a signal processing module, a central control module, a display module and a monitoring alarm module;
the monitor module is connected with the central control module, consists of an electroencephalogram signal monitor, an electrocardiosignal monitor, a pulse signal monitor, a respiration signal monitor, a muscle signal monitor and a perception stimulator and is used for acquiring real-time body state signals of patients;
the signal processing module is connected with the central control module and comprises a signal collector and an amplifying circuit, wherein the signal collector is used for collecting the body state signal collected by the monitor, the signal is amplified through the amplifying circuit, the signal is denoised by using wavelet packet denoising after amplification, the wavelet packet denoising can process noise generated in the transmission process of the signal, and the integrity of the signal is ensured;
after the signal collector collects the body state signal, the signal collector carries out primary processing on the body state signal, and the processing method comprises the following steps:
generating an estimated signal value for a particular signal component in the input signal;
the calculation formula of the estimated signal value is as follows:
wherein i is a positive integer and is equal to or less than the number of types of the input signal, K is a positive integer and is equal to or less than the number K of the nodes,for the estimated signal value, S, corresponding to the i-th input signali(n) is the i-th input signal, xk(n) is the input signal of the kth node;
generating a signal processing result according to the input signal and the estimated signal value;
adjusting the estimated signal value according to the signal processing result to output a target estimated signal of a specific signal component in the input signal;
the central control module is connected with the monitor module, the signal processing module, the display module, the data monitoring module and the monitoring alarm module, comprises a controller, an A/D converter and a D/A converter, and is used for processing feedback signals of all machines and realizing transmission of control signals;
the processing of the feedback signals of the various machines comprises: determining a linear relationship between a physical quantity of an AD conversion object and a corresponding voltage value; judging whether the voltage value measured under the current physical quantity has deviation, and if the deviation exists, automatically performing AD conversion calibration by the controller;
the controller automatically performs AD conversion calibration, including:
connecting and setting parameters of the controller and testing the operating characteristics of the controller; the operational characteristics of the test controller include: the controller is enabled to be in a speed mode, so that the controller is enabled to control and correct, and the stable performance of the speed inner ring is ensured; the designed MFAC control algorithm is built on an upper PC through Simulink of cSPACE; running a compilation module in the MFAC controller; automatically generating DSP codes by using an MFAC algorithm; downloading the codes into a digital signal processor through a USB interface of an upper PC for operation, generating a voltage output signal through a controller, and driving the controller to operate;
the MFAC control method is realized by programming:
the MFAC controller u (k) is built partially based on Simulink of cSPACE, and lambda > 0 is a weight coefficient and is used for limiting the change of a control input quantity; rho epsilon (0, 1)]The step size factor is additionally added, so that the algorithm has stronger flexibility and generality;is an estimate of phi (k) at time k; y (k +1) is the desired output signal; u (k), y (k) respectively represent the input and output of the system at time k;
the MFAC controller u (k) is built in part from Simulink of cSPACE, and comprises:
u (k) is subjected to a time delay module to obtain u (k-1); a Sine Wave module in the cSPACE gives a sinusoidal position signal, namely, y (k + 1); the output y (k +1) of the linear motor can be obtained by the grating detection unit, and then y (k) is obtained by the delay module; the lambda and rho values in the MFAC control law algorithm can be directly adjusted online by WM-Write2 and WM-Write3 in cSPACE; the output of the estimator is connected to the In end of the Subsystem, and the output Out is obtainedy (k) is connected to the desired signal y (k +1) in a negative feedback manner, thereby obtaining y (k +1) -y (k); the output is inserted into the Product module to obtainAccessing the output sum u (k-1) into the Add block, wherein Listofsigns in the Add block is set to (+ + -E); obtaining an output signal u (k) of the MFAC controller;
wherein, mu is more than 0, eta belongs to (0, 1)];The pseudo-partial derivative of the previous time instant of representation;
Δy(k)=y(k)-y(k-1);Δu(k-1)=u(k-1)-u(k-2);
substituting the pseudo partial derivatives into the formulaThereby obtaining a controller output u (k);
the controller outputs u (k), and then the digital signal is converted into an analog signal through the D/A converter; the analog signal is regenerated into a voltage output signal to drive operation;
the display module is connected with the central control module and is formed by connecting three display screens, the left display screen is used for displaying pulse signals and muscle signals, the middle display screen is used for displaying brain signals, electrocardio signals and respiratory signals, and the right display screen is used for displaying perception stimulation signals and anesthesia depth data;
the data monitoring module is connected with the central control module and is used for analyzing the data transmitted by the central control module in real time and screening whether abnormal data exist or not;
and the alarm module is connected with the central control module and used for sending alarm prompt by using the alarm when abnormal data is detected.
2. The anesthesia depth monitoring system of claim 1, wherein the data monitoring module comprises a data reading unit, a data screening unit, an abnormal database unit and a parameter setting unit, and the screening method of the abnormal data by the data monitoring module comprises:
setting a data range value for screening the acquired data through a parameter setting unit;
the data reading unit is connected with the central control module and reads various processed body state signals;
screening data which accord with the data range value set by the parameter setting unit through the data screening unit, and outputting corresponding statistical abnormal data;
and the abnormal database is connected with the data screening unit and is used for storing the data screened by the data screening unit.
3. The anesthesia depth monitoring system of claim 2, wherein the screening of the data conforming to the data range values set by the parameter setting unit by the data screening unit comprises:
screening in a first round, namely screening out data which belong to systematic errors in the data of various body state signals to obtain body state signal data after the first round of screening;
screening for the second round, namely screening out data which do not accord with actual body conditions in the body state signal data after the first round of screening to obtain body state signal data after the second round of screening;
and a third round of screening, namely screening abnormal and continuous data in the body state signal data after the second round of screening to obtain body state signal data after the third round of screening.
4. The anesthesia depth monitoring system of claim 1, wherein the means for amplifying the signal by the amplification circuit comprises:
receiving body state signals collected by a signal collector, and respectively sending the body state signals to a coil branch and a reference branch;
in the coil branch, the transmitting coil transmits an electromagnetic signal, the receiving coil receives an induced signal, and an output signal of the receiving coil is amplified;
and then sent to a central control module for processing, wherein the central control module generates an adjustable amplification control signal to further control the adjustable amplifier.
5. The system of claim 4, wherein a phase shifter is disposed in one of the coil branch or the reference branch, the phase shifter shifting the phase of the branch signal in response to a phase shift control signal.
6. The anesthesia depth monitoring system of claim 1, wherein the alarm module comprises an audible and visual alarm for emitting an audible and visual alarm signal and a wireless signal transmitter for transmitting the alarm signal to a remote monitoring terminal.
7. The system of claim 1, wherein the cardiac signal monitor, the muscle signal monitor and the brain signal monitor are used for real-time signal acquisition of the patient through an electrode patch.
8. The anesthesia depth monitoring system of claim 1, further comprising:
the data storage module is connected with the central control module and is used for realizing the real-time storage of the patient information through the memory;
and the evaluation module is connected with the central control module and used for sending a request for requesting data to the central control module through an evaluation program, the request information reaches the switch, the switch is sent to the router, the router is sent to the server of the DNS server reaching the main controller, the server receives the request for requesting data, the data to be counted are packaged and packaged, the original path is returned to the evaluation module, the data are decoded, and the current anesthesia depth of the patient is analyzed through the evaluation program.
9. The anesthesia depth monitoring system of claim 8, wherein the evaluation program performs a computational evaluation of the data using a trained deep convolutional neural network, comprising:
annotating the body state signal data to establish a training data set comprising a first assessment score;
training the deep convolutional neural network through a training data set to reduce a difference between a second evaluation score output by the deep convolutional neural network corresponding to the input body state signal and a first evaluation score of the input body state signal through training.
10. The anesthesia depth monitoring system of claim 9, wherein the first assessment score is a preliminary quality assessment of the body state signal based on a predetermined anesthesia depth parameter.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110327529.4A CN113100709A (en) | 2021-03-26 | 2021-03-26 | Anesthesia depth monitoring system and anesthesia depth monitoring method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110327529.4A CN113100709A (en) | 2021-03-26 | 2021-03-26 | Anesthesia depth monitoring system and anesthesia depth monitoring method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113100709A true CN113100709A (en) | 2021-07-13 |
Family
ID=76712349
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110327529.4A Pending CN113100709A (en) | 2021-03-26 | 2021-03-26 | Anesthesia depth monitoring system and anesthesia depth monitoring method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113100709A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114366030A (en) * | 2021-12-31 | 2022-04-19 | 中国科学院苏州生物医学工程技术研究所 | Intelligent auxiliary system and method for anesthesia operation |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102540221A (en) * | 2010-10-31 | 2012-07-04 | 联发科技股份有限公司 | Signal processing apparatus and signal processing method |
US20120277548A1 (en) * | 2009-08-14 | 2012-11-01 | David Burton | Anaesthesia and consciousness depth monitoring system |
CN103297048A (en) * | 2012-03-01 | 2013-09-11 | 深圳市蓝韵实业有限公司 | Self-calibration AD converter and AD conversion method thereof |
CN106897748A (en) * | 2017-03-02 | 2017-06-27 | 上海极链网络科技有限公司 | Face method for evaluating quality and system based on deep layer convolutional neural networks |
CN109462356A (en) * | 2018-12-06 | 2019-03-12 | 北京信息科技大学 | A kind of MFA control method of servo system for linear motor |
CN110141230A (en) * | 2019-04-24 | 2019-08-20 | 陕西省人民医院 | A kind of anesthesia depth monitor and anesthesia depth monitoring method |
CN110908985A (en) * | 2019-11-01 | 2020-03-24 | 苏州热工研究院有限公司 | Intelligent screening method and system for abnormal data of meteorological environment automatic monitoring station |
CN111061163A (en) * | 2019-12-31 | 2020-04-24 | 北京黎明文仪家具有限公司 | Household furniture fire control system, method and device based on Internet of things |
CN111938656A (en) * | 2020-07-28 | 2020-11-17 | 南京审计大学 | Real-time walking mode identification method and system based on knee joint exoskeleton |
-
2021
- 2021-03-26 CN CN202110327529.4A patent/CN113100709A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20120277548A1 (en) * | 2009-08-14 | 2012-11-01 | David Burton | Anaesthesia and consciousness depth monitoring system |
CN102540221A (en) * | 2010-10-31 | 2012-07-04 | 联发科技股份有限公司 | Signal processing apparatus and signal processing method |
CN103297048A (en) * | 2012-03-01 | 2013-09-11 | 深圳市蓝韵实业有限公司 | Self-calibration AD converter and AD conversion method thereof |
CN106897748A (en) * | 2017-03-02 | 2017-06-27 | 上海极链网络科技有限公司 | Face method for evaluating quality and system based on deep layer convolutional neural networks |
CN109462356A (en) * | 2018-12-06 | 2019-03-12 | 北京信息科技大学 | A kind of MFA control method of servo system for linear motor |
CN110141230A (en) * | 2019-04-24 | 2019-08-20 | 陕西省人民医院 | A kind of anesthesia depth monitor and anesthesia depth monitoring method |
CN110908985A (en) * | 2019-11-01 | 2020-03-24 | 苏州热工研究院有限公司 | Intelligent screening method and system for abnormal data of meteorological environment automatic monitoring station |
CN111061163A (en) * | 2019-12-31 | 2020-04-24 | 北京黎明文仪家具有限公司 | Household furniture fire control system, method and device based on Internet of things |
CN111938656A (en) * | 2020-07-28 | 2020-11-17 | 南京审计大学 | Real-time walking mode identification method and system based on knee joint exoskeleton |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114366030A (en) * | 2021-12-31 | 2022-04-19 | 中国科学院苏州生物医学工程技术研究所 | Intelligent auxiliary system and method for anesthesia operation |
CN114366030B (en) * | 2021-12-31 | 2024-04-09 | 中国科学院苏州生物医学工程技术研究所 | Intelligent auxiliary system and method for anesthesia operation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8070677B2 (en) | Method and apparatus for distinguishing between clinically significant changes and artifacts in patient physiological information | |
US4365636A (en) | Method of monitoring patient respiration and predicting apnea therefrom | |
CN103717128B (en) | For selecting the method and apparatus of differential input lead | |
US20140350355A1 (en) | Monitoring and managing sleep breathing disorders | |
EP2688468A1 (en) | Apparatus and method for measuring physiological signal quality | |
EP2787881A1 (en) | Ventricular fibrillation detection | |
JP2008536627A (en) | Multiple sensors for sleep apnea that indicate probabilities for sleep diagnosis and means for automatically triggering alarms or treatments | |
US10524680B2 (en) | Electrocardiogram device and methods | |
JP2009148372A (en) | Stress determining system and stress relieving system | |
JP2000508191A (en) | Device for measuring depth of anesthesia | |
CN108492890B (en) | Human health state monitoring system and method | |
CN107320095B (en) | Electrocardio monitoring method and electrocardio monitoring equipment | |
KR101111498B1 (en) | Depth of anesthesia monitoring system and method using bio-signal analysis and learning process | |
CN113100709A (en) | Anesthesia depth monitoring system and anesthesia depth monitoring method | |
CN114176564B (en) | Method for extracting respiratory state based on radar signal | |
CN107530014A (en) | For system, method and the computerized algorithm of the change for measuring, showing and accurately detect electro physiology Evoked ptential | |
Mufarid et al. | Central Monitor Based On Personal Computer Using One Wireless Receiver | |
CN112107293B (en) | Snore monitoring system based on breathing parameters during sleep | |
CN113724851A (en) | Intelligent synchronization method of breathing machine and data visualization system thereof | |
JP2012509732A (en) | Methods for diagnosis and treatment of wounds and screening for electrical markers for prognosis of wounds | |
CN107982615B (en) | Optimized pressure titration method and device | |
CN113397501A (en) | Nephropathy detection method based on big data | |
CN113749620B (en) | Sleep apnea detection method, system, equipment and storage medium | |
CN114743659A (en) | Medical equipment management system based on multiple filtering | |
CN117894461A (en) | Sleep quality assessment method, system, device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |